Hugging Face's logo

giuseppemartino
/
model1

Image Segmentation
Transformers
PyTorch
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
model1 / README.md
giuseppemartino's picture
giuseppemartino
End of training
0f5de6c
preview code
|
raw
history blame
No virus
12.8 kB
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - image-segmentation
  - vision
  - generated_from_trainer
model-index:
  - name: model1
    results: []

model1

This model is a fine-tuned version of nvidia/mit-b0 on the giuseppemartino/i-SAID_custom_or_1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2328
  • Mean Iou: 0.1042
  • Mean Accuracy: 0.1313
  • Overall Accuracy: 0.2017
  • Accuracy Background: nan
  • Accuracy Ship: 0.5956
  • Accuracy Small-vehicle: 0.0476
  • Accuracy Tennis-court: 0.5923
  • Accuracy Helicopter: nan
  • Accuracy Basketball-court: 0.0
  • Accuracy Ground-track-field: 0.0098
  • Accuracy Swimming-pool: 0.0
  • Accuracy Harbor: 0.3785
  • Accuracy Soccer-ball-field: 0.0
  • Accuracy Plane: 0.0
  • Accuracy Storage-tank: 0.0
  • Accuracy Baseball-diamond: 0.0
  • Accuracy Large-vehicle: 0.2151
  • Accuracy Bridge: 0.0
  • Accuracy Roundabout: 0.0
  • Iou Background: 0.0
  • Iou Ship: 0.4621
  • Iou Small-vehicle: 0.0458
  • Iou Tennis-court: 0.5337
  • Iou Helicopter: nan
  • Iou Basketball-court: 0.0
  • Iou Ground-track-field: 0.0097
  • Iou Swimming-pool: 0.0
  • Iou Harbor: 0.2993
  • Iou Soccer-ball-field: 0.0
  • Iou Plane: 0.0
  • Iou Storage-tank: 0.0
  • Iou Baseball-diamond: 0.0
  • Iou Large-vehicle: 0.2124
  • Iou Bridge: 0.0
  • Iou Roundabout: 0.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 6e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: polynomial
  • training_steps: 1200

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Background Accuracy Ship Accuracy Small-vehicle Accuracy Tennis-court Accuracy Helicopter Accuracy Basketball-court Accuracy Ground-track-field Accuracy Swimming-pool Accuracy Harbor Accuracy Soccer-ball-field Accuracy Plane Accuracy Storage-tank Accuracy Baseball-diamond Accuracy Large-vehicle Accuracy Bridge Accuracy Roundabout Iou Background Iou Ship Iou Small-vehicle Iou Tennis-court Iou Helicopter Iou Basketball-court Iou Ground-track-field Iou Swimming-pool Iou Harbor Iou Soccer-ball-field Iou Plane Iou Storage-tank Iou Baseball-diamond Iou Large-vehicle Iou Bridge Iou Roundabout
1.9822 1.0 105 1.2892 0.0989 0.1440 0.2348 nan 0.4735 0.0 0.8169 nan 0.0 0.0 0.0 0.4963 0.0 0.0 0.0 0.0 0.2296 0.0 0.0 0.0 0.2526 0.0 0.6683 nan 0.0 0.0 0.0 0.3355 0.0 0.0 0.0 0.0 0.2269 0.0 0.0
1.2543 2.0 210 0.8623 0.0866 0.1170 0.2348 nan 0.1505 0.0 0.8538 nan 0.0 0.0 0.0 0.4055 0.0 0.0 0.0 0.0 0.2275 0.0 0.0 0.0 0.0861 0.0 0.7363 nan 0.0 0.0 0.0 0.2519 0.0 0.0 0.0 0.0 0.2248 0.0 0.0
0.8713 3.0 315 0.5622 0.0639 0.0761 0.1772 nan 0.0095 0.0 0.5983 nan 0.0 0.0 0.0 0.2609 0.0 0.0 0.0 0.0 0.1963 0.0 0.0 0.0 0.0091 0.0 0.5714 nan 0.0 0.0 0.0 0.1821 0.0 0.0 0.0 0.0 0.1953 0.0 0.0
0.5934 4.0 420 0.4178 0.0698 0.0859 0.2062 nan 0.0156 0.0 0.5852 nan 0.0 0.0 0.0 0.3260 0.0 0.0 0.0 0.0 0.2754 0.0 0.0 0.0 0.0137 0.0 0.5481 nan 0.0 0.0 0.0 0.2149 0.0 0.0 0.0 0.0 0.2706 0.0 0.0
0.4793 5.0 525 0.3240 0.0518 0.0630 0.1120 nan 0.1356 0.0005 0.4301 nan 0.0 0.0 0.0 0.2204 0.0 0.0 0.0 0.0 0.0954 0.0 0.0 0.0 0.1177 0.0005 0.3972 nan 0.0 0.0 0.0 0.1673 0.0 0.0 0.0 0.0 0.0951 0.0 0.0
0.3711 6.0 630 0.2836 0.0736 0.0930 0.1310 nan 0.4607 0.0002 0.5083 nan 0.0 0.0000 0.0 0.2322 0.0 0.0 0.0 0.0 0.1002 0.0 0.0 0.0 0.3787 0.0002 0.4270 nan 0.0 0.0000 0.0 0.1978 0.0 0.0 0.0 0.0 0.0998 0.0 0.0
0.347 7.0 735 0.2647 0.0988 0.1242 0.1963 nan 0.5288 0.0160 0.5769 nan 0.0 0.0001 0.0 0.3912 0.0 0.0 0.0 0.0 0.2261 0.0 0.0 0.0 0.4020 0.0159 0.5461 nan 0.0 0.0001 0.0 0.2955 0.0 0.0 0.0 0.0 0.2223 0.0 0.0
0.3004 8.0 840 0.2667 0.1135 0.1445 0.2693 nan 0.5257 0.0617 0.6456 nan 0.0 0.0006 0.0 0.4247 0.0 0.0 0.0 0.0 0.3640 0.0 0.0 0.0 0.4010 0.0590 0.5757 nan 0.0 0.0006 0.0 0.3104 0.0 0.0 0.0 0.0 0.3557 0.0 0.0
0.2622 9.0 945 0.2399 0.0856 0.1053 0.1591 nan 0.4918 0.0207 0.5720 nan 0.0 0.0001 0.0 0.2555 0.0 0.0 0.0 0.0 0.1344 0.0 0.0 0.0 0.4010 0.0203 0.5078 nan 0.0 0.0001 0.0 0.2207 0.0 0.0 0.0 0.0 0.1334 0.0 0.0
0.2489 10.0 1050 0.2446 0.1002 0.1257 0.1846 nan 0.5400 0.0391 0.5641 nan 0.0 0.0030 0.0 0.4262 0.0 0.0 0.0 0.0 0.1880 0.0 0.0 0.0 0.4294 0.0379 0.5256 nan 0.0 0.0030 0.0 0.3212 0.0 0.0 0.0 0.0 0.1860 0.0 0.0
0.242 11.0 1155 0.2346 0.0957 0.1198 0.1773 nan 0.5657 0.0261 0.5443 nan 0.0 0.0024 0.0 0.3529 0.0 0.0 0.0 0.0 0.1854 0.0 0.0 0.0 0.4501 0.0257 0.4917 nan 0.0 0.0024 0.0 0.2829 0.0 0.0 0.0 0.0 0.1834 0.0 0.0
0.2276 11.43 1200 0.2328 0.1042 0.1313 0.2017 nan 0.5956 0.0476 0.5923 nan 0.0 0.0098 0.0 0.3785 0.0 0.0 0.0 0.0 0.2151 0.0 0.0 0.0 0.4621 0.0458 0.5337 nan 0.0 0.0097 0.0 0.2993 0.0 0.0 0.0 0.0 0.2124 0.0 0.0

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1